audit-paper
Audit a paper's empirical claims against the linked code repository — catches MISMATCH, MISSING, and PARTIAL claims before submission
A command is the one you type. It runs exactly when you ask it to, and never before.
4,566 commands across 357 plugins.
Audit a paper's empirical claims against the linked code repository — catches MISMATCH, MISSING, and PARTIAL claims before submission
Creative research brainstorming — generate ideas researchers within a single field would miss. Cross-field connections, assumption challenges, alternative…
Write one specific section of a paper as complete paragraphs. Use when you already have context and just need one section drafted. Follows writing-engine…
Migrate existing agent system to Claude Code best practices architecture
Setup or migrate a Claude Code plugin — detect, select, validate, refactor
Scan the session, suggest candidate learnings, and deepen the ones you pick
Save a structured snapshot of the current Ableton session state - tracks, devices, key parameters, tempo - to a markdown file. Use as a checkpoint before risky…
Generate optimized BigQuery SQL from a natural language description. Pass a description of the data you need.
Optimize BigQuery SQL by fixing all detected anti-patterns. Pass a file path or paste SQL directly.
Review BigQuery SQL for performance anti-patterns. Pass a file path or paste SQL directly.
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).
Continue working on a change - create the next artifact (Experimental)
Scaffold a new scaffolding-compatible skill: an interactive flow that creates `skills/<name>/SKILL.md` from the canonical template, composes a `TRIGGER`/`SKIP`…
Run initial setup — install dependencies, configure optional features, verify environment
Run the parallel Auto-Harness orchestration flow with worktree workers. /auto-harness:harness-parallel <brief or clarification/spec-approval reply>
Run the Planner side only. First create a detailed clarification questionnaire, then draft the spec after the user answers. /auto-harness:plan <brief or…
Run the parallel Planner side only. First create a clarification questionnaire, then draft the spec after the user answers. /auto-harness:plan-parallel <brief…
Implement a story according to the requirements and tasks
Learn story-flow concepts with interactive guidance for junior developers
Review a story markdown, optionally against a Jira/ClickUp story
프로젝트에 맞는 CLAUDE.md 한국어 템플릿을 생성합니다. 웹앱, API 서버, 데이터 파이프라인, 모노레포, 사이드 프로젝트 유형을 지원합니다. Use when the user wants to create or set up CLAUDE.md in Korean.
Complete and close a PRD after PR is merged to production
Create new PRD with interactive refinement and AI assistance
Verify project structure aligns with official Claude Code standards
Exports cookies from tandem's Chrome via CDP (includes HttpOnly/Secure). Filter with --domain <d>. Formats: list (table, default), json, curl, headers,…
HTTP sniffer for tandem's Chrome via CDP: captures request+response bodies (including HttpOnly, CSRF tokens, private APIs). Subcommands: start, show, clear,…
Captures the current page in tandem's Chrome as a PDF (if headless Chrome) or full-page PNG screenshot (in normal tandem mode). Saves to…
Login flows, password UX, 2FA/passkey, session management, permission prompts, trust signals
Enterprise patterns, RBAC UI, multi-tenant, complex onboarding, admin dashboards
Visual identity, logo usage, brand colors, typography as brand expression
Interactive, section-by-section restructuring of a story into the canonical template through a collaborative conversation. Slower than `improve` on purpose.
List active AKA detection exceptions (masked) from the local store
接着委派任务继续(续子进程线程)。默认续本目录上次;也可凭模糊描述点名续任意历史/跨目录 session。读/写模式自动继承——不需要重传 --write。
委派模型对本地 git 改动做代码审查。只读不改文件。--adversarial 切对抗式设计审查;可用 --<modelKey> 指定模型
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic